long-task

Warn

Audited by Socket on May 13, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

The skill’s capabilities mostly match its stated purpose as a long-running project orchestrator, and there is no clear credential theft or exfiltration path. The main issue is proportionality: it normalizes sustained autonomous coding, command execution, merging, and continuation without per-action user approval, which makes it high risk operationally even though it does not appear malicious.

Confidence: 86%Severity: 74%
Audit Metadata
Analyzed At
May 13, 2026, 10:34 AM
Package URL
pkg:socket/skills-sh/chann%2Fskills%2Flong-task%2F@37c7eb15cbd3e738ed8e0ea342887798878ff91e